Kaiyue Feng
Papers
1
Total Citations
2
H-Index
1
About
Kaiyue Feng is a researcher at the forefront of robotic manipulation and computer vision, with a focus on real-time grasping systems. Her most cited work introduces a two-stage full convolutional neural network that dramatically reduces visual processing time for robotic grasp prediction, addressing a critical bottleneck in autonomous robotics. By simplifying the network architecture while maintaining high accuracy, Feng’s algorithm enables robots to detect and execute grasps in dynamic environments with unprecedented speed—a contribution that has garnered attention for its practical implications in industrial automation and service robotics. Though early in her career, her 2021 paper has already earned 2 citations, reflecting growing interest in efficient deep learning solutions for real-world robotic tasks. Feng’s work bridges the gap between theoretical computer vision and applied robotics, offering a streamlined approach that balances computational efficiency with robust performance. Her research is particularly valuable for students and engineers seeking to deploy neural networks on resource-constrained robotic platforms, and it positions her as an emerging voice in the quest for more responsive, intelligent machines.
Research Focus
Key Achievements
Top Papers
- 1Grasping Prediction Algorithm Based on Full Convolutional Neural Network2 citations · 2021